install
pip install torch numpy transformers datasets tiktoken wandb tqdm
Dependencies:
- pytorch
- numpy
transformers
for huggingface transformersdatasets
for huggingface datasets (preprocess OpenWebText test and validation bin)tiktoken
for OpenAI's fast BPE codewandb
for optional loggingtqdm
for progress bars
quick start
Inference:
$ python inference.py
Thanks
Zero To Hero series. Specifically, the GPT video is popular if you have some prior language modeling context.